Wan 2.1

Wan 2.1
Alibaba Cloud · Video Generation
POST /v1/videos/generations

Alibaba’s Wan 2.1 video model with turbo and plus tiers for text-to-video, image-to-video, and first and last frame clips at 480p or 720p.

At a glance

FieldValue
Model idwan-2-1
Model release date2025-02-25
Input modalitiesText, Image
Output modalitiesVideo
Context window-
Weight precision-
RegionSingapore
Featurestext_to_video, image_to_video
Native inferenceNo
NewNo
Supported endpointsPOST /v1/videos/generations
Alternate model idsalibaba/wan-2.1, wan2.1

Pricing

ChargeSpecRate
Turboper second$0.036
Plusper second$0.10

Example request

$curl https://api.empiriolabs.ai/v1/videos/generations \
> -H 'Authorization: Bearer $EMPIRIOLABS_API_KEY' \
> -H 'Content-Type: application/json' \
> -d '{"model": "wan-2-1", "prompt": "sunrise over the ocean", "duration": 6}'

Parameters

ParameterTypeRequiredDefaultDescription
promptstringyes-Scene description.
modeenumno"auto"Auto detects from attachments. t2v: text-to-video. i2v: animate one image. kf2v: interpolate between a first and last frame (two images). · Allowed: auto, t2v, i2v, kf2v
model_tierenumno"turbo"turbo: faster and cheaper, 480p or 720p. plus: higher fidelity, 720p only. First-last frame always uses plus. · Allowed: turbo, plus
resolutionenumno"720p"480p is turbo-only. · Allowed: 480p, 720p
aspect_ratioenumno"16:9"Used for text-to-video; image modes follow the source image. 480p supports 16:9, 9:16, and 1:1 only. · Allowed: 16:9, 9:16, 1:1, 4:3, 3:4
imagestringno-Source image URL. i2v uses one image; kf2v uses two (first and last frame).
durationnumberno5Clip length in seconds. Only turbo i2v supports 3 to 5; every other mode renders 5. · Range: 3 – 5
negative_promptstringno""What to avoid.
seednumberno-Reproducibility seed.
prompt_extendbooleannotrueLet the service rewrite the prompt for better results.
watermarkbooleannofalseAdd a provenance watermark to the output.

Notes

Clips render about 5 seconds without audio; turbo image-to-video supports 3 to 5 seconds. Turbo outputs 480p or 720p, plus outputs 720p. Two attached images run first and last frame interpolation on the plus tier.


Machine-readable schema: GET https://api.empiriolabs.ai/v1/models/wan-2-1.